How to Use the Outlier Detection Engine MCP in OpenAI Agents SDK

Q: Can I use Z-Score thresholds with Outlier Detection Engine in my OpenAI Agents SDK pipeline?

Yes. You can instruct your agent to call the detectoutliers tool with a specific Z-score threshold like 3.0. The OpenAI Agents SDK automatically handles the JSON schema validation, ensuring the model passes a valid float value to the server.

Run deterministic outlier checks inside your OpenAI Agents SDK workflows without letting models guess statistical boundaries.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Outlier Detection Engine MCP to OpenAI Agents SDK

Create your Vinkius account to connect Outlier Detection Engine to OpenAI Agents SDK — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Outlier Detection Engine with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Mathematical Guardrails for OpenAI Agents SDK

Stop letting your GPT-4 agents guess which data points are anomalies based on vibes. By registering the Outlier Detection Engine as an MCP Server, your agents get immediate, deterministic access to standard IQR and Z-Score math directly through the `detect_outliers` tool. This means your agent can process raw numeric columns, execute the math locally, and get back precise indices of bad data. No more expensive LLM reasoning cycles wasted on basic statistical checks.

Safe Multi-Agent Handoffs on Clean Data

Clean data is the foundation of reliable agent execution. When your primary ingestion agent runs `detect_outliers`, it can immediately hand off the cleaned dataset to a specialized analysis agent using the OpenAI Agents SDK routing system. If the tool flags too many anomalies, the guardrails halt the workflow before any bad data hits your downstream OpenAI dashboards. You get clean runs and predictable API costs.

Zero-Config Tool Discovery

Hooking this up takes seconds. Pass the MCPServerStreamableHttp instance straight to your Agent constructor and let the SDK auto-discover the `detect_outliers` capabilities using the MCP standard. By enabling the cacheToolsList option, your production agents load the schema instantly without querying the server on every single loop. It keeps your latency low and your code clean.

Setup guide

Set up Outlier Detection Engine MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Outlier Detection Engine tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Outlier Detection Engine tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Outlier Detection Engine tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Outlier Detection Engine Agent",
            instructions="You have access to Outlier Detection Engine tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by simple-statistics. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Outlier Detection Engine now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Outlier Detection Engine MCP in OpenAI Agents SDK

The tool processes numeric columns locally using fast math. Your OpenAI Agents SDK setup doesn't need to upload raw CSVs to OpenAI's servers; it just sends the column data to the local MCP Server endpoint and gets the outlier indices back.

Yes. You can instruct your agent to call the `detect_outliers` tool with a specific Z-score threshold like 3.0. The OpenAI Agents SDK automatically handles the JSON schema validation, ensuring the model passes a valid float value to the server.

Writing python code on the fly is slow and prone to runtime errors. Using this dedicated MCP Server ensures your OpenAI Agents SDK agent uses pre-tested, deterministic IQR logic every single time without writing buggy code.

Set the timeout directly inside your MCPServerStreamableHttp parameters. This prevents your agent from hanging if you pass a massive dataset containing millions of rows to the `detect_outliers` tool.

Your numeric data never leaves the Vinkius sandbox. The MCP Server executes the statistical calculations in an isolated V8 environment, ensuring your proprietary financial or operational metrics are never exposed to external networks or used for training.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript